Overview
FIRE, the Flexible Image Retrieval Engine, is a content-based image retrieval system that I developed in cooperation with many other people at the Human Language Technology and Pattern Recognition Group of RWTH Aachen University.
The main aim of FIRE is to investigate different image descriptors and evaluate their performance. FIRE was developed in C++ and Python and is meant to be eaily extensible.
FIRE was started during my diploma thesis and then progressively extended.
Contributors include
- Daniel Keysers (initial version, lots of help)
- Andre Hegerath (sparse histograms)
- Tobias Weyand (combination with text retrieval)
- Helga Velroyen (reimplementation of some feature extractors, some helper scripts)
- Jens Forster (on demand feature loading)
- Christian Terboven (openMP parallelization)
- Fabian Schwahn (upload of query images and querying with subimages)
- Christian Kofler (FireWatch)
- Piotr Bininski (C# library to access a FIRE server)
- Tobias Gass (Diversity)
- insert your name here by contributing
Downloads
Currently FIRE is available from my old RWTH Aachen CS department website.
I hope to release a new version on a google code site soon (including some bug fixes for compiler compatibility and the diversity features).
Demo
An online demo with photographs is available here.
Another demo with medical images is available here.
Normally these servers are up and running. If not, please let me know. I will restart it.
The people from the Image Understanding and Pattern Recognition Group from Kaiserslautern have extended FIRE for sub image retrieval and created a very nice demo video:
Publications
If you use FIRE within your research, I would be happy if you would cite a paper of mine. For example:
Thomas Deselaers, Daniel Keysers, Hermann Ney Features for Image Retrieval: An Experimental Comparison. Information Retrieval. 2008.
Vol. 11. Issue 2. Springer. pp. 77-107.
If you are unsure which paper to cite, feel free to contact me.